Website Auditor MCP

What changed in AI visibility

get_changes

Read-only

Compare two website audits that asked the same question to report overall and per-engine AI-visibility score changes and what rose or fell.

Instructions

Report what changed in a website's AI-visibility score, only between two snapshots that asked the same question. Use this when someone asks "did anything change," "what's different this week/month," or "did my AI visibility drop." The domain need not be tracked: history accrues from any audit of it, tracked or not — track_site adds the weekly re-audits to the series, it is not a precondition, so do not track a site just to answer a change question. Returns the change in the overall score and the per-engine score changes, for engines measured both times — the overall only when the same engines answered both snapshots, otherwise it is null with an overall_note naming which answered each, and the per-engine changes stand alone; competitor_changes, new_issues and resolved_issues are always empty, since snapshots record neither competitors nor audit issues. A change is only ever measured between two snapshots that asked the same question (the same business name, market and queries); when there is no such pair it says why instead of giving a number, with the date the series re-baselined when it did. The series is the measured weekly re-audits and any audit that asked the same question as the newest recorded one, while it has no gap longer than four weeks and a day from the newest weekly re-audit that recorded its question, through each later snapshot of the series (weekly re-audits included, recorded or not), to the newest measured snapshot; otherwise every measured snapshot. Requires a Website Auditor subscription ($10/month; eligible new customers get a 7-day free trial — payment method required, no charge until the trial ends) — if the user doesn't have one, call get_sample_audit first to show them the exact output format, free and with no API key.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`since`	No	Optional ISO date or "last_check".
`domain`	Yes	The website domain, e.g. "example.com".

Output Schema

TableJSON Schema

Name	Required	Description
`note`	No	Present when skipped_snapshots is above 0, when the two snapshots compared were answered by different engines, when newer measured snapshots were left out of the series, or when newer weekly re-audits measured nothing of the business: which, and why, in words. Relay it.
`new_issues`	Yes	Always empty: AI-visibility snapshots record no audit issues. Kept for clients that read it.
`score_delta`	Yes	Only ever between two snapshots that asked the same question AND were answered by the same engines. When there is no such pair, including a re-baseline after the business name, market or queries changed, the tool returns NOT_YET_AVAILABLE saying so, never a number; when the pair exists but different engines answered the two snapshots, the overall is not subtracted and is null with overall_note, and engine_changes still compares every engine that answered both.
`overall_note`	No	Present exactly when score_delta is null: the two snapshots were answered by different engines, and which answered each. Relay it — a null delta for this reason must not read like a null for want of history.
`engine_changes`	Yes
`to_captured_at`	No	When the later one was.
`resolved_issues`	Yes	Always empty: AI-visibility snapshots record no audit issues. Kept for clients that read it.
`from_captured_at`	No	When the earlier snapshot compared was captured.
`skipped_snapshots`	No	Snapshots passed over because they asked a different question (another business name, market or queries) or do not record what they asked.
`competitor_changes`	Yes	Always empty: AI-visibility snapshots record no competitors. Kept for clients that read it.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedv1.0.25Oct 1, 2026

changedOutput schema / properties / note / description

Previous value: -"Present when skipped_snapshots is above 0, when newer measured snapshots were left out of the series, or when newer weekly re-audits measured nothing of the business: which, and why, in words. Relay it."New value: +"Present when skipped_snapshots is above 0, when the two snapshots compared were answered by different engines, when newer measured snapshots were left out of the series, or when newer weekly re-audits measured nothing of the business: which, and why, in words. Relay it."

addedOutput schema / properties / overall_note

Added value: +{
+  "description": "Present exactly when score_delta is null: the two snapshots were answered by different engines, and which answered each. Relay it — a null delta for this reason must not read like a null for want of history.",
+  "type": "string"
+}

changedOutput schema / properties / score_delta / description

Previous value: -"Only ever between two snapshots that asked the same question. When there is no such pair, including a re-baseline after the business name, market or queries changed, the tool returns NOT_YET_AVAILABLE saying so, never a number."New value: +"Only ever between two snapshots that asked the same question AND were answered by the same engines. When there is no such pair, including a re-baseline after the business name, market or queries changed, the tool returns NOT_YET_AVAILABLE saying so, never a number; when the pair exists but different engines answered the two snapshots, the overall is not subtracted and is null with overall_note, and engine_changes still compares every engine that answered both."

changedOutput schema / properties / score_delta / type

Previous value: -"number"New value: +[
+  "number",
+  "null"
+]

Changed8 schema fields changedv1.0.24Sep 17, 2026

addedOutput schema / properties / competitor_changes / description

Added value: +"Always empty: AI-visibility snapshots record no competitors. Kept for clients that read it."

addedOutput schema / properties / from_captured_at

Added value: +{
+  "description": "When the earlier snapshot compared was captured.",
+  "type": "string"
+}

addedOutput schema / properties / new_issues / description

Added value: +"Always empty: AI-visibility snapshots record no audit issues. Kept for clients that read it."

addedOutput schema / properties / note

Added value: +{
+  "description": "Present when skipped_snapshots is above 0, when newer measured snapshots were left out of the series, or when newer weekly re-audits measured nothing of the business: which, and why, in words. Relay it.",
+  "type": "string"
+}

addedOutput schema / properties / resolved_issues / description

Added value: +"Always empty: AI-visibility snapshots record no audit issues. Kept for clients that read it."

addedOutput schema / properties / score_delta / description

Added value: +"Only ever between two snapshots that asked the same question. When there is no such pair, including a re-baseline after the business name, market or queries changed, the tool returns NOT_YET_AVAILABLE saying so, never a number."

addedOutput schema / properties / skipped_snapshots

Added value: +{
+  "description": "Snapshots passed over because they asked a different question (another business name, market or queries) or do not record what they asked.",
+  "type": "number"
+}

addedOutput schema / properties / to_captured_at

Added value: +{
+  "description": "When the later one was.",
+  "type": "string"
+}

Changed1 schema field changedv1.0.23Sep 9, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "competitor_changes": {
+      "items": {},
+      "type": "array"
+    },
+    "engine_changes": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "delta": {
+            "type": "number"
+          },
+          "engine": {
+            "type": "string"
+          },
+          "from": {
+            "type": "number"
+          },
+          "to": {
+            "type": "number"
+          }
+        },
+        "required": [
+          "engine",
+          "from",
+          "to",
+          "delta"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "new_issues": {
+      "items": {},
+      "type": "array"
+    },
+    "resolved_issues": {
+      "items": {},
+      "type": "array"
+    },
+    "score_delta": {
+      "type": "number"
+    }
+  },
+  "required": [
+    "score_delta",
+    "engine_changes",
+    "competitor_changes",
+    "new_issues",
+    "resolved_issues"
+  ],
+  "type": "object"
+}

First observedv1.0.6Jul 29, 2026

TDQS

A4.5/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare the safe read-only profile, yet the description adds substantial behavior: the null-overall rule when engines differ (with overall_note), that competitor_changes/new_issues/resolved_issues are always empty, the re-baselining date reporting, gating on a paid Website Auditor subscription, and the get_sample_audit fallback. This is well beyond what annotations supply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and triggers are correctly front-loaded, but the single-paragraph block is bloated and the 'series' sentence ('no gap longer than four weeks and a day from the newest weekly re-audit that recorded its question, through each later snapshot...') is nearly impenetrable. Some return-field narration is redundant given the output schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with an output schema and rich annotations, the description is more complete than needed, covering prerequisites, pricing/trial terms, the empty-field guarantees, and the no-valid-pair behavior. Nothing an agent needs to select or invoke it is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters are already documented and the baseline is 3. The description's series/time analysis implicitly informs how far back the change is measured, but it never explicitly maps to the `since` parameter ('last_check') nor explains a domain-vs-question mismatch.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Report what changed in a website's AI-visibility score') and immediately scopes it to 'only between two snapshots that asked the same question.' This carving distinguishes it from siblings like get_ai_visibility, get_report, and compare_competitors without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit triggers are quoted verbatim ('did anything change,' 'what's different this week/month,' 'did my AI visibility drop'), and it names when NOT to use a sibling: 'do not track a site just to answer a change question,' clarifying that track_site adds re-audits but 'is not a precondition.' When/when-not/alternative are all covered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server